bella-archetypes

Synthesize consensus, divergence, and recommendations from multi-voice archetype panels.

8|3|Updated Feb 8, 2026

Search Tags:#archetypes #voice-generation #brand-coherence #bellaassist #panel-evaluation #market-reception

Ready to run

npx skills add https://github.com/haberlah/dotfiles-claude --skill bella-archetypes

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: bella-archetypes
Source: https://github.com/haberlah/dotfiles-claude/tree/main/skills/bella-archetypes
Command: npx skills add https://github.com/haberlah/dotfiles-claude --skill bella-archetypes

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

BellaAssist archetype evaluation panels solve the problem of fragmented, inconsistent brand feedback by authenticating messages through multiple predefined agent voices.

Core Features & Use Cases

Panel models: SC, P, and Org perspectives (and a full 9-voice panel), applicable to brand positioning, pricing, and messaging validation across enterprise and participant-facing contexts.
Named pairs and debate presets for tension tests; reference panel guide for divergence signals.
Reference-driven synthesis: consensus, divergence, recommendations with confidence notes.
Use case: a marketing team validating BellaAssist positioning before a launch by running a full 9-voice panel.

Quick Start

Run the preferred panel (e.g., all voices or a subset) and load the appropriate agent cards and references to generate voices and synthesis.

Frequently Asked Questions about bella-archetypes

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I validate brand positioning using a virtual archetype panel?▼

Brand positioning validation through a virtual archetype panel runs predefined agent voices across SC, P, and Org perspectives to synthesize consensus, divergence, and actionable recommendations from loaded references.

What is multi-voice feedback generation for brand concept testing?▼

Multi-voice feedback generation authenticates brand concepts by simulating a full 9-voice panel, producing structured synthesis that highlights consensus and divergence across enterprise and participant-facing messaging scenarios.

Can I run a subset of archetype voices instead of the full 9-voice panel?▼

Yes, you can run preferred panel subsets, such as SC, P, or Org perspectives individually, alongside named pairs and debate presets for targeted tension tests before generating synthesis.

What references and agent data do I need to set up a brand coherence evaluation?▼

Brand coherence evaluation requires loading appropriate agent-card data and reference materials into the panel, which then leverages these inputs to generate multi-voice outputs and confidence notes.

When should I use named pairs and debate presets in market reception evaluation?▼

Use named pairs and debate presets during market reception evaluation to conduct targeted tension tests, specifically designed to surface divergence signals and validate messaging alignment before launch.

Does panel evaluation support pricing and messaging validation across different contexts?▼

Panel evaluation supports pricing and messaging validation across both enterprise branding and participant-facing contexts, authenticating messages by synthesizing feedback from multiple predefined agent voices.